Programme

Tuesday 18 October 

Kobe International Conference Center

14:00 – 14:10: Welcome

14:10 – 14:50: Invited Talk: Gerard de Melo – Knowledge Graphs: Venturing out into the Wild

In the past years, knowledge graphs have grown from niche academic
endeavours to becoming important assets for many IT companies. Yet,
although we now have vast repositories of facts at our disposal, it
appears that our systems often need further kinds of knowledge that are
still missing in most knowledge graphs. In this talk, I will argue that
we need keep moving further beyond simple collections of encyclopedic
facts, and that natural language is the key to these new forms of
knowledge. The talk will showcase several of our contributions towards
this goal. These include our work on large lexical knowledge graphs such
as UWN/MENTA and Lexvo.org, on integrated semantic resources such as
FrameBase, and on large-scale common-sense knowledge collections such as
WebChild and Knowlywood.
Bio:
Gerard de Melo is joining Rutgers, The State University of New Jersey as
an Assistant Professor in the Department of Computer Science. He
previously served as an Assistant Professor at Tsinghua University,
Beijing, heading the Web Mining and Language Technology group. Over the
years, he has published over 70 research papers, with Best Paper awards
at CIKM 2010, ICGL 2008, and the NAACL 2015 Workshop on Vector Space
Modeling, as well as an ACL 2014 Best Paper Honorable Mention, a Best
Student Paper Award nomination at ESWC 2015, and the WWW 2011 Best
Demonstration Award, among others. Prior to joining Tsinghua, de Melo
had spent two years as a Visiting Scholar at UC Berkeley, working in the
ICSI AI group. He received his doctoral degree at the Max Planck
Institute for Informatics in Germany. For more information, please refer
to his home page at http://gerard.demelo.org.

 

14:50 – 15:30: Session 1: Multimedia 

14:50 – 15:10: Information Extraction from the Web by Matching Visual Presentation Patterns – Radek Burget. [preprint]

15:10 – 15:30: Wikipedia and DBpedia For Media – Managing Audiovisual Resources In Their Semantic Context – Jean-Pierre Evain, Tormod Vaervagen and Mike Matton. [preprint

15:30 – 16:00: Coffee Break

16:00 – 16:40: Session 2: Inducing Knowledge

16:00 – 16:20: Statistical Induction of Coupled Domain/Range Restrictions from RDF Knowledge Bases – Basil Ell, Sherzod Hakimov and Philipp Cimiano. [preprint]

16:20 – 16:40: Entity Typing using Distributional Semantics and DBpedia – Marieke van Erp and Piek Vossen [preprint]

16:40 – 17:25: Session 3: Working session & discussion

17:25 – 17:30: closing